技術(shù)路線：
python+requests+re

代碼如下：

import requests
from bs4 import BeautifulSoup
import re

def getHTMLcode(url,data):
    try:
        r = requests.get(url, headers=data)
        print(r.status_code)
        r.raise_for_status()
        print(r.apparent_encoding)
        r.encoding = r.apparent_encoding
        print(r.encoding)
        return r.text,r.encoding
    except:
        print('爬取失敗')

def parsePage(contain,html):
    soup = BeautifulSoup(html, "html.parser")
    # find_all( name , attrs , recursive , text , **kwargs )
    items = soup.find_all(name='div', class_='article')
    for item in items:
        print(item)
        print('-------------------------------')
        item = str(item)
        a = []
        # 發(fā)布人，發(fā)布內(nèi)容，發(fā)布時(shí)間，點(diǎn)贊數(shù)
        pattern = re.compile(
            r'<div class="author clearfix">.*?<h2>(.*?)</h2>.*?<span>(.*?)</span>.*?<i class="number">(.*?)</i>', re.S)
        groups = re.findall(pattern, item)  #groups是以元組為元素的列表

        for g in groups:    #g是元組
            a.append(g[0])
            a.append(g[1])
            a.append(g[2])
        contain.append(a)


def saveArticle(contain,filPath):
    for article in contain:
        with open(filPath,'a+',encoding='utf-8') as f:
            temp='作者:'+article[0].strip('\n')+'\n'+'內(nèi)容:\n'+article[1].strip('\n').replace('<br/>', '')+'\n點(diǎn)贊數(shù):'+article[2].strip('\n')+'\n\n\n\n'
            f.write(temp)

def spyder(url,data,depth,filPath):
    for i in range(depth):
        url=url+str(depth+11)
        html,encoding=getHTMLcode(url, data)
        if encoding=='ISO-8859-2':
            continue
        contain=[]
        parsePage(contain, html)
        saveArticle(contain,filPath)

if __name__=="__main__":
    depth =10
    url = 'https://www.qiushibaike.com/hot/page/'
    data = {'User-Agent': 'Mozilla/5.0'}
    filPath='newarticle.docx'
    spyder(url,data,depth,filPath)

關(guān)鍵點(diǎn)：
正則表達(dá)式的編寫：
pattern = re.compile(
r'<div class="author clearfix">.?<h2>(.?)</h2>.?<span>(.?)</span>.?<i class="number">(.?)</i>', re.S)
說明：
1：(.*?)代表分組懒鉴，用正則的方法re.findall(pattern, item)每個(gè)匹配的字符串里面我們先要的部分會以元組的形式返回冻记，然后一篇文章里有多組匹配的字符串的話最終結(jié)果會返回以元組為元素的列表锭环。
2：re.S代表.包括匹配換行